The text-to-image script is experimental, and it’s easy to overfit and run into issues like catastrophic forgetting. Try exploring different hyperparameters to get the best results on your dataset.
Text-to-image models like Stable Diffusion are conditioned to generate images given a text prompt.
Training a model can be taxing on your hardware, but if you enable
mixed_precision, it is possible to train a model on a single 24GB GPU. If you’re training with larger batch sizes or want to train faster, it’s better to use GPUs with more than 30GB of memory. You can reduce your memory footprint by enabling memory-efficient attention with xFormers. JAX/Flax training is also supported for efficient training on TPUs and GPUs, but it doesn’t support gradient checkpointing, gradient accumulation or xFormers. A GPU with at least 30GB of memory or a TPU v3 is recommended for training with Flax.
This guide will explore the train_text_to_image.py training script to help you become familiar with it, and how you can adapt it for your own use-case.
Before running the script, make sure you install the library from source:
git clone https://github.com/huggingface/diffusers
pip install .
Then navigate to the example folder containing the training script and install the required dependencies for the script you’re using:
pip install -r requirements.txt
🤗 Accelerate is a library for helping you train on multiple GPUs/TPUs or with mixed-precision. It’ll automatically configure your training setup based on your hardware and environment. Take a look at the 🤗 Accelerate Quick tour to learn more.
Initialize an 🤗 Accelerate environment:
To setup a default 🤗 Accelerate environment without choosing any configurations:
accelerate config default
Or if your environment doesn’t support an interactive shell, like a notebook, you can use:
from accelerate.utils import write_basic_config write_basic_config()
Lastly, if you want to train a model on your own dataset, take a look at the Create a dataset for training guide to learn how to create a dataset that works with the training script.
The following sections highlight parts of the training script that are important for understanding how to modify it, but it doesn’t cover every aspect of the script in detail. If you’re interested in learning more, feel free to read through the script and let us know if you have any questions or concerns.
The training script provides many parameters to help you customize your training run. All of the parameters and their descriptions are found in the
parse_args() function. This function provides default values for each parameter, such as the training batch size and learning rate, but you can also set your own values in the training command if you’d like.
For example, to speedup training with mixed precision using the fp16 format, add the
--mixed_precision parameter to the training command:
accelerate launch train_text_to_image.py \
Some basic and important parameters include:
--pretrained_model_name_or_path: the name of the model on the Hub or a local path to the pretrained model
--dataset_name: the name of the dataset on the Hub or a local path to the dataset to train on
--image_column: the name of the image column in the dataset to train on
--caption_column: the name of the text column in the dataset to train on
--output_dir: where to save the trained model
--push_to_hub: whether to push the trained model to the Hub
--checkpointing_steps: frequency of saving a checkpoint as the model trains; this is useful if for some reason training is interrupted, you can continue training from that checkpoint by adding
--resume_from_checkpointto your training command
The Min-SNR weighting strategy can help with training by rebalancing the loss to achieve faster convergence. The training script supports predicting
epsilon (noise) or
v_prediction, but Min-SNR is compatible with both prediction types. This weighting strategy is only supported by PyTorch and is unavailable in the Flax training script.
--snr_gamma parameter and set it to the recommended value of 5.0:
accelerate launch train_text_to_image.py \ --snr_gamma=5.0
You can compare the loss surfaces for different
snr_gamma values in this Weights and Biases report. For smaller datasets, the effects of Min-SNR may not be as obvious compared to larger datasets.
The dataset preprocessing code and training loop are found in the
main() function. If you need to adapt the training script, this is where you’ll need to make your changes.
train_text_to_image script starts by loading a scheduler and tokenizer. You can choose to use a different scheduler here if you want:
noise_scheduler = DDPMScheduler.from_pretrained(args.pretrained_model_name_or_path, subfolder="scheduler")
tokenizer = CLIPTokenizer.from_pretrained(
args.pretrained_model_name_or_path, subfolder="tokenizer", revision=args.revision
Then the script loads the UNet model:
load_model = UNet2DConditionModel.from_pretrained(input_dir, subfolder="unet")
Next, the text and image columns of the dataset need to be preprocessed. The
tokenize_captions function handles tokenizing the inputs, and the
train_transforms function specifies the type of transforms to apply to the image. Both of these functions are bundled into
images = [image.convert("RGB") for image in examples[image_column]]
examples["pixel_values"] = [train_transforms(image) for image in images]
examples["input_ids"] = tokenize_captions(examples)
Lastly, the training loop handles everything else. It encodes images into latent space, adds noise to the latents, computes the text embeddings to condition on, updates the model parameters, and saves and pushes the model to the Hub. If you want to learn more about how the training loop works, check out the Understanding pipelines, models and schedulers tutorial which breaks down the basic pattern of the denoising process.
Once you’ve made all your changes or you’re okay with the default configuration, you’re ready to launch the training script! 🚀
Let’s train on the Pokémon BLIP captions dataset to generate your own Pokémon. Set the environment variables
dataset_name to the model and the dataset (either from the Hub or a local path). If you’re training on more than one GPU, add the
--multi_gpu parameter to the
accelerate launch command.
To train on a local dataset, set the
OUTPUT_DIR environment variables to the path of the dataset and where to save the model to.
accelerate launch --mixed_precision="fp16" train_text_to_image.py \
--resolution=512 --center_crop --random_flip \
--lr_scheduler="constant" --lr_warmup_steps=0 \
Once training is complete, you can use your newly trained model for inference:
from diffusers import StableDiffusionPipeline
pipeline = StableDiffusionPipeline.from_pretrained("path/to/saved_model", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
image = pipeline(prompt="yoda").images
Congratulations on training your own text-to-image model! To learn more about how to use your new model, the following guides may be helpful: